Nonlinear diffusion system for simultaneous restoration and binarization of degraded document images. (English) Zbl 1538.94006
Summary: Existing diffusion models can only do tasks for either restoration or binarization of degraded document images; in this paper, we pay close attention to the problem of simultaneous restoration and binarization. We first introduce a model of image formation for degraded document images, which decomposes a degraded document image into the product of background and foreground components. Then a weakly coupled nonlinear diffusion system is developed for simultaneous restoration and binarization of degraded document images. In this diffusion system, the first equation is used to estimate background component and the second equation is responsible for the foreground component. The restored and binarized images are finally obtained by the estimated background and foreground components, respectively. Two coupled diffusion equations are solved alternately by explicit finite differencing. The proposed model is tested on some degraded document images that represent five types of typical degradations including bleed-through, complex background, page stains, stamps and smeared ink, and is compared with eight closely related models for degraded document binarization, qualitatively and quantitatively. Experimental results illustrate that the proposed model has shown promising results in terms of restoration and binarization of degrade document images.
MSC:
| 94A08 | Image processing (compression, reconstruction, etc.) in information and communication theory |
| 68U10 | Computing methodologies for image processing |
| 35K57 | Reaction-diffusion equations |
| 65M06 | Finite difference methods for initial value and initial-boundary value problems involving PDEs |
| 65D18 | Numerical aspects of computer graphics, image analysis, and computational geometry |
References:
| [1] | He, S.; Schomaker, L., CT-Net: cascade T-shape deep fusion networks for document binarization. Pattern Recognit. (2021) |
| [2] | Oldřich, K.; Michal, H., TG(2): text-guided transformer GAN for restoring document readability and perceived quality. Int. J. Doc. Anal. Recognit., 15-28 (2022) |
| [3] | Perona, P.; Malik, J., Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell., 7, 629-639 (1990) |
| [4] | Riya; Gupta, B.; Lamba, S. S., An efficient anisotropic diffusion model for image denoising with edge preservation. Comput. Math. Appl., 106-119 (2021) · Zbl 1524.94030 |
| [5] | Li, C.; He, C., Fractional-order diffusion coupled with integer-order diffusion for multiplicative noise removal. Comput. Math. Appl., 34-43 (2023) · Zbl 1538.65254 |
| [6] | Bettahar, S.; Lambert, P.; Stambouli, A. B., PDE-based efficient method for colour image restoration. Comput. Math. Appl., 3, 577-590 (2017) · Zbl 1391.94058 |
| [7] | Majee, S.; Jain, S. K.; Ray, R. K.; Majee, A. K., On the development of a coupled nonlinear telegraph-diffusion model for image restoration. Comput. Math. Appl., 7, 1745-1766 (2020) · Zbl 1490.65157 |
| [8] | Theljani, A.; Belhachmi, Z.; Moakher, M., High-order anisotropic diffusion operators in spaces of variable exponents and application to image inpainting and restoration problems. Nonlinear Anal., Real World Appl., 251-271 (2019) · Zbl 1414.65030 |
| [9] | Halim, A.; Kumar, B. R., An anisotropic PDE model for image inpainting. Comput. Math. Appl., 9, 2701-2721 (2020) · Zbl 1524.94017 |
| [10] | Yang, J.; Guo, Z.; Zhang, D.; Wu, B.; Du, S., An anisotropic diffusion system with nonlinear time-delay structure tensor for image enhancement and segmentation. Comput. Math. Appl., 29-44 (2022) · Zbl 1538.94017 |
| [11] | Yang, J.; Guo, Z.; Wu, B.; Du, S., A nonlinear anisotropic diffusion model with non-standard growth for image segmentation. Appl. Math. Lett. (2023) · Zbl 1538.94016 |
| [12] | Ifeoma, N.; Zhixin, S.; Venu, G., PDE-based enhancement of low quality documents, 541-545 |
| [13] | Fadoua, D.; Frank, L.; Hubert, E., A new PDE-based approach for singularity-preserving regularization: application to degraded characters restoration. Int. J. Doc. Anal. Recognit., 183-212 (2012) |
| [14] | Guemri, K.; Drira, F., Adaptative shock filter for image characters enhancement and denoising, 279-283 |
| [15] | Guo, J.; He, C., Adaptive shock-diffusion model for restoration of degraded document images. Appl. Math. Model., 555-565 (2020) · Zbl 1481.65129 |
| [16] | Du, Z.; He, C., Nonlinear diffusion equation with selective source for binarization of degraded document images. Appl. Math. Model., 243-259 (2021) · Zbl 1481.94013 |
| [17] | Wang, Y.; Zhou, L.; Zhang, X., Spatio-temporal regularized shock-diffusion filtering with local entropy for restoration of degraded document images. Appl. Math. Comput. (2023) · Zbl 07689966 |
| [18] | Jacobs, B.; Momoniat, E., A novel approach to text binarization via a diffusion-based model. Appl. Math. Comput., 446-460 (2013) · Zbl 1334.68279 |
| [19] | Jacobs, B.; Momoniat, E., A locally adaptive, diffusion based text binarization technique. Appl. Math. Comput., 464-472 (2015) · Zbl 1410.94010 |
| [20] | Guo, J.; He, C.; Zhang, X., Nonlinear edge-preserving diffusion with adaptive source for document images binarization. Appl. Math. Comput., 8-22 (2019) · Zbl 1428.94025 |
| [21] | Guo, J.; He, C.; Wang, Y., Fourth order indirect diffusion coupled with shock filter and source for text binarization. Signal Process. (2020) |
| [22] | Zhang, X.; He, C.; Guo, J., Selective diffusion involving reaction for binarization of bleed-through document images. Appl. Math. Model., 844-854 (2020) · Zbl 1481.94045 |
| [23] | Jacobs, B.; Celik, T., Unsupervised document image binarization using a system of nonlinear partial differential equations. Appl. Math. Comput. (2022) · Zbl 1510.94015 |
| [24] | Du, Z.; He, C., Anisotropic diffusion with fuzzy-based source for binarization of degraded document images. Appl. Math. Comput. (2023) |
| [25] | Feng, S., A novel variational model for noise robust document image binarization. Neurocomputing, 288-302 (2019) |
| [26] | Feng, S., Effective document image binarization via a convex variational level set model. Appl. Math. Comput. (2022) · Zbl 1510.94010 |
| [27] | Chris, T.; Tony, M., Historical document image binarization: a review. SN Comput. Sci., 173 (2020) |
| [28] | Whitaker, R.; Xue, X., Variable-conductance, level-set curvature for image denoising, 142-145 |
| [29] | Miller, R. K.; Michel, A. N., Ordinary Differential Equations (1982), Academic Press · Zbl 0552.34001 |
| [30] | Zhang, X.; He, C., Robust double-weighted guided image filtering. Signal Process. (2022) |
| [31] | Bella, F. Z.A.; Rhabi, M. E.; Hakim, A.; Laghrib, A., Reduction of the non-uniform illumination using nonlocal variational models for document image analysis. J. Franklin Inst., 16, 8225-8244 (2018) · Zbl 1398.94020 |
| [32] | Pratikakis, I.; Zagoris, K.; Barlas, G.; Gatos, B., ICFHR2014 competition on handwritten document image binarization (H-DIBCO 2014), 619-623 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
